eachlabs-voice-audio

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill accepts and fetches arbitrary external URLs (e.g., media_url, audio_url, file_url, source_url, and custom_rvc_model_download_url shown in the Examples and Parameter Reference) and then transcribes/uses that untrusted third-party audio or model content as part of its workflow, which could carry indirect prompt-injection.